Update README.md
Browse files
README.md
CHANGED
|
@@ -12,4 +12,6 @@ A tiny 55 million parameter model trained on 1.3 billion tokens using a custom d
|
|
| 12 |
|
| 13 |
The tokenizer is a basic bpe tokenizer that was trained on a smaller subset of 80_000 samples of this same data mixture with a vocab size of 8000.
|
| 14 |
|
| 15 |
-
This model has not undergone any post-training.
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
The tokenizer is a basic bpe tokenizer that was trained on a smaller subset of 80_000 samples of this same data mixture with a vocab size of 8000.
|
| 14 |
|
| 15 |
+
This model has not undergone any post-training.
|
| 16 |
+
|
| 17 |
+
This base model is best suited for fine-tuning on specific tasks. On its own, it very limited, but it is a pretty flexible foundation for applications such as toxic comment detection or sentiment analysis.
|